agentrigs
+ submit rig
~ / rigs / fjerbi / claude-code-arsenal

fjerbi/claude-code-arsenal

A tested Claude Code operating system for efficient, reliable, and focused software engineering. Includes global instructions, workflows, rules, and tools designed to minimize wasted tokens, prevent hallucinations and unnecessary loops, enf

↗ GitHub ★ 2 MIT updated 4d ago project Claude CodeCodex
share on X
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
CONTEXT TAX · EVERY TURN
~4.0k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Blocks destructive commands · Pre-tool screening hook · details

Copy this rig

# review before running: this installs third-party code
$ npx degit fjerbi/claude-code-arsenal/.claude ./rig-claude-code-arsenal  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit fjerbi/claude-code-arsenal/.claude/skills/nextjs .claude/skills/nextjs
$ curl -fsSL --create-dirs -o .claude/agents/fixer.md https://raw.githubusercontent.com/fjerbi/claude-code-arsenal/main/.claude/agents/fixer.md
$ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/fjerbi/claude-code-arsenal/main/.claude/agents/orchestrator.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/fjerbi/claude-code-arsenal/main/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/fjerbi/claude-code-arsenal/main/.claude/agents/researcher.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/fjerbi/claude-code-arsenal/main/.claude/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/validator.md https://raw.githubusercontent.com/fjerbi/claude-code-arsenal/main/.claude/agents/validator.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(rm -rf /*)",
      "Bash(rm -rf ~)",
      "Bash(curl:* | bash)",
      "Bash(curl:* | sh)",
      "Bash(chmod -R 777 /)",
      "Bash(git push --force:*)",
      "Bash(git push -f:*)",
      "Bash(git reset --hard:*)",
      "Bash(git clean -fd:*)",
      "Bash(git checkout -- .)",
      "Bash(find / -delete)",
      "Bash(mkfs:*)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash \"$CLAUDE_PROJECT_DIR/.claude/hooks/guard-bash.sh\""
          }
        ]
      }
    ]
  }
}

Skills (1)

nextjs

Subagents (6)

fixer
model: opus
Resolves a proven root cause with the smallest reliable patch, applying TDD where the project supports it and verifying with real command output. Use for bug fixes and scoped implementation work once
orchestrator
model: opus
>-
planner
model: sonnet
Turns a research-backed objective into a minimal, dependency-ordered, verifiable execution plan with parallel-branch identification and per-step verification checkpoints. Use before implementing COMPL
researcher
model: sonnet
Read-only fact-gathering agent — locates exact files, symbols, and call chains, and reports confirmed facts vs. assumptions with file:line evidence. Use PROACTIVELY before any COMPLEX/CRITICAL change
reviewer
model: sonnet
Reviews a diff for correctness, scope creep, safety, and security against the original objective and verification evidence, and renders ACCEPT/REVISE/BLOCK with findings ranked by severity. Use before
validator
model: sonnet
Runs the smallest verification that proves a change works — targeted tests, type checks, or smoke checks — and reports pass/fail with actual command output, never assertions. Use after any code change

Hooks (4)

eventmatcherruns
SessionStart*bash "$CLAUDE_PROJECT_DIR/.claude/hooks/session-context.sh"
PreToolUseBashbash "$CLAUDE_PROJECT_DIR/.claude/hooks/guard-bash.sh"
PostToolUseWrite|Edit|MultiEditbash "$CLAUDE_PROJECT_DIR/.claude/hooks/verify-files.sh" edit
Stop*bash "$CLAUDE_PROJECT_DIR/.claude/hooks/verify-files.sh" stop

Slash commands (11)

/auto/debug-root-cause/fix-bug/implement-feature/plan-task/quality-gate/review-architecture/review-diff/safety-review/triage-task/validate-change

Permissions

deny (14)
Bash(sudo:*)
Bash(rm -rf /)
Bash(rm -rf /*)
Bash(rm -rf ~)
Bash(curl:* | bash)
Bash(curl:* | sh)
Bash(chmod -R 777 /)
Bash(git push --force:*)
Bash(git push -f:*)
Bash(git reset --hard:*)
Bash(git clean -fd:*)
Bash(git checkout -- .)
Bash(find / -delete)
Bash(mkfs:*)
ask (0)
—
allow (8)
Bash
Read
Write
Edit
MultiEdit
Glob
Grep
Task

Similar rigs

jaqubowsky/fleet
Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox and brings back tested, reviewed pull requests.
★ 12 project Claude CodeCodex 3 agents today
Minimalist 341 tok ·
Alex5350/arsenal
Provider-agnostic AI development hub: one docs/ source of truth for skills, standards, tiered model routing, and work tracking across Claude Code, Codex CLI, OpenCode, and GitHub Copilot
★ 0 project Claude CodeCodexCopilot 5 skills 3 agents 20d ago
Pragmatist 1.7k tok ·
OMOCHInoHOSHI/dotfiles-claude
.claude
★ 1 setup Claude Code 4 agents 3mo ago
Pragmatist 293 tok ·
tylerjkells/claude-dotfiles
—
★ 0 setup Claude Code 4 agents 8mo ago
Pragmatist 579 tok ·
copied ✓